模型预测算法优化
This commit is contained in:
parent
a1d9c60e61
commit
ee9ba299fa
@ -185,13 +185,14 @@ const startPrediction = async () => {
|
||||
try {
|
||||
predicting.value = true
|
||||
const payload = {
|
||||
training_mode: 'global', // 明确指定训练模式
|
||||
model_type: form.model_type,
|
||||
version: form.version,
|
||||
future_days: form.future_days,
|
||||
start_date: form.start_date,
|
||||
analyze_result: form.analyze_result
|
||||
}
|
||||
const response = await axios.post('/api/predict', payload)
|
||||
const response = await axios.post('/api/prediction', payload)
|
||||
if (response.data.status === 'success') {
|
||||
predictionResult.value = response.data.data
|
||||
ElMessage.success('预测完成！')
|
||||
|
||||
@ -167,3 +167,34 @@
|
||||
- **状态**: **所有已知问题已修复**。
|
||||
- **确认**: 用户已确认“现在药品和店铺预测流程通了”。
|
||||
- **后续**: 将本次修复过程归档至本文档。
|
||||
|
||||
|
||||
---
|
||||
|
||||
### 2025年7月16日 18:38 - 全模型预测功能通用性修复
|
||||
|
||||
**问题现象**:
|
||||
在解决了 `Transformer` 模型的预测问题后，发现一个更深层次的系统性问题：在所有预测模式（按药品、按店铺、全局）中，只有 `Transformer` 算法可以成功预测并显示图表，而其他四种模型（`mLSTM`, `KAN`, `优化版KAN`, `TCN`）虽然能成功训练，但在预测时均会失败，并提示“没有可用于图表的数据”。
|
||||
|
||||
**根本原因深度分析**:
|
||||
这个问题的核心在于**模型配置的持久化不完整且不统一**。
|
||||
|
||||
1. **Transformer 的“幸存”**: `Transformer` 模型的实现恰好不依赖于那些在保存时被遗漏的特定超参数，因此它能“幸存”下来。
|
||||
2. **其他模型的“共性缺陷”**: 其他所有模型 (`mLSTM`, `TCN`, `KAN`) 在它们的构造函数中，都依赖于一些在训练时定义、但在保存到检查点文件 (`.pth`) 时**被遗漏的**关键结构性参数。
|
||||
* **mLSTM**: 缺少 `mlstm_layers`, `embed_dim`, `dense_dim` 等参数。
|
||||
* **TCN**: 缺少 `num_channels`, `kernel_size` 等参数。
|
||||
* **KAN**: 缺少 `hidden_sizes` 列表。
|
||||
3. **连锁失败**:
|
||||
* 当 `server/predictors/model_predictor.py` 尝试加载这些模型的检查点文件时，它从 `checkpoint['config']` 中找不到实例化模型所必需的全部参数。
|
||||
* 模型实例化失败，抛出 `KeyError` 或 `TypeError`。
|
||||
* 这个异常导致 `load_model_and_predict` 函数提前返回 `None`，最终导致返回给前端的响应中缺少 `history_data`，前端因此无法渲染图表。
|
||||
|
||||
**系统性、可扩展的解决方案**:
|
||||
为了彻底解决这个问题，并为未来平稳地加入新算法，我们对所有非 Transformer 的训练器进行了标准化的、彻底的修复。
|
||||
|
||||
1. **修复 `mlstm_trainer.py`**: 在 `config` 字典中补全了 `mlstm_layers`, `embed_dim`, `dense_dim` 等所有缺失的参数。
|
||||
2. **修复 `tcn_trainer.py`**: 在 `config` 字典中补全了 `num_channels`, `kernel_size` 等所有缺失的参数。
|
||||
3. **修复 `kan_trainer.py`**: 在 `config` 字典中补全了 `hidden_sizes` 列表。
|
||||
|
||||
**结果**:
|
||||
通过这次系统性的修复，我们确保了所有训练器在保存模型时，都会将完整的、可用于重新实例化模型的配置信息写入检查点文件。这从根本上解决了所有模型算法的预测失败问题，使得整个系统在处理不同算法时具有了通用性和健壮性。
|
||||
|
||||
Binary file not shown.
@ -1508,35 +1508,40 @@ def predict():
|
||||
"""
|
||||
try:
|
||||
data = request.json
|
||||
product_id = data.get('product_id')
|
||||
model_type = data.get('model_type')
|
||||
store_id = data.get('store_id')
|
||||
training_mode = 'store' if store_id else 'product'
|
||||
version = data.get('version') # 新增版本参数
|
||||
version = data.get('version')
|
||||
future_days = int(data.get('future_days', 7))
|
||||
start_date = data.get('start_date', '')
|
||||
include_visualization = data.get('include_visualization', False)
|
||||
|
||||
scope_msg = f", store_id={store_id}" if store_id else ", 全局模型"
|
||||
print(f"API接收到预测请求: product_id={product_id}, model_type={model_type}, version={version}{scope_msg}, future_days={future_days}, start_date={start_date}")
|
||||
|
||||
if not product_id or not model_type:
|
||||
return jsonify({"status": "error", "error": "product_id 和 model_type 是必需的"}), 400
|
||||
# 确定训练模式和标识符
|
||||
training_mode = data.get('training_mode', 'product')
|
||||
product_id = data.get('product_id')
|
||||
store_id = data.get('store_id')
|
||||
|
||||
# 获取产品名称
|
||||
product_name = get_product_name(product_id)
|
||||
if not product_name:
|
||||
product_name = product_id
|
||||
|
||||
# 根据训练模式构建模型标识符
|
||||
if training_mode == 'store':
|
||||
if training_mode == 'global':
|
||||
# 全局模式：使用硬编码的标识符，并为预测函数设置占位符
|
||||
model_identifier = "global_all_products_sum"
|
||||
product_id = 'all_products'
|
||||
product_name = "全局聚合数据"
|
||||
elif training_mode == 'store':
|
||||
# 店铺模式：验证store_id并构建标识符
|
||||
if not store_id:
|
||||
return jsonify({"status": "error", "error": "店铺模式需要 store_id"}), 400
|
||||
model_identifier = f"store_{store_id}"
|
||||
# 对于店铺预测，product_id实际上是store_id，但我们需要一个药品ID来获取名称，这里暂时用一个占位符
|
||||
product_name = f"店铺 {store_id} 整体"
|
||||
else:
|
||||
else: # 默认为 'product' 模式
|
||||
# 药品模式：验证product_id并构建标识符
|
||||
if not product_id:
|
||||
return jsonify({"status": "error", "error": "药品模式需要 product_id"}), 400
|
||||
model_identifier = product_id
|
||||
product_name = get_product_name(product_id) or product_id
|
||||
|
||||
print(f"API接收到预测请求: mode={training_mode}, model_identifier='{model_identifier}', model_type='{model_type}', version='{version}'")
|
||||
|
||||
if not model_type:
|
||||
return jsonify({"status": "error", "error": "model_type 是必需的"}), 400
|
||||
|
||||
# 获取模型版本
|
||||
if not version:
|
||||
version = get_latest_model_version(model_identifier, model_type)
|
||||
@ -3818,7 +3823,9 @@ def get_store_model_versions_api(store_id, model_type):
|
||||
def get_global_model_versions_api(model_type):
|
||||
"""获取全局模型版本列表API"""
|
||||
try:
|
||||
model_identifier = "global"
|
||||
# 全局模型的标识符是在训练时确定的，例如 'global_all_products_sum'
|
||||
# 这里我们假设前端请求的是默认的全局模型
|
||||
model_identifier = "global_all_products_sum"
|
||||
versions = get_model_versions(model_identifier, model_type)
|
||||
latest_version = get_latest_model_version(model_identifier, model_type)
|
||||
|
||||
|
||||
@ -191,6 +191,7 @@ class PharmacyPredictor:
|
||||
if model_type == 'transformer':
|
||||
model_result, metrics, actual_version = train_product_model_with_transformer(
|
||||
product_id=product_id,
|
||||
model_identifier=model_identifier,
|
||||
product_df=product_data,
|
||||
store_id=store_id,
|
||||
training_mode=training_mode,
|
||||
@ -208,6 +209,7 @@ class PharmacyPredictor:
|
||||
elif model_type == 'mlstm':
|
||||
_, metrics, _, _ = train_product_model_with_mlstm(
|
||||
product_id=product_id,
|
||||
model_identifier=model_identifier,
|
||||
product_df=product_data,
|
||||
store_id=store_id,
|
||||
training_mode=training_mode,
|
||||
@ -223,6 +225,7 @@ class PharmacyPredictor:
|
||||
elif model_type == 'kan':
|
||||
_, metrics = train_product_model_with_kan(
|
||||
product_id=product_id,
|
||||
model_identifier=model_identifier,
|
||||
product_df=product_data,
|
||||
store_id=store_id,
|
||||
training_mode=training_mode,
|
||||
@ -236,6 +239,7 @@ class PharmacyPredictor:
|
||||
elif model_type == 'optimized_kan':
|
||||
_, metrics = train_product_model_with_kan(
|
||||
product_id=product_id,
|
||||
model_identifier=model_identifier,
|
||||
product_df=product_data,
|
||||
store_id=store_id,
|
||||
training_mode=training_mode,
|
||||
@ -249,6 +253,7 @@ class PharmacyPredictor:
|
||||
elif model_type == 'tcn':
|
||||
_, metrics, _, _ = train_product_model_with_tcn(
|
||||
product_id=product_id,
|
||||
model_identifier=model_identifier,
|
||||
product_df=product_data,
|
||||
store_id=store_id,
|
||||
training_mode=training_mode,
|
||||
|
||||
@ -113,11 +113,17 @@ def load_model_and_predict(product_id, model_type, store_id=None, future_days=7,
|
||||
)
|
||||
store_name = product_df['store_name'].iloc[0] if 'store_name' in product_df.columns and not product_df.empty else f"店铺{store_id}"
|
||||
prediction_scope = f"店铺 '{store_name}' ({store_id})"
|
||||
# 对于店铺模型，其“产品名称”就是店铺名称
|
||||
product_name = store_name
|
||||
elif training_mode == 'global':
|
||||
# 全局模型：聚合所有数据
|
||||
product_df = aggregate_multi_store_data(
|
||||
aggregation_method='sum',
|
||||
file_path=DEFAULT_DATA_PATH
|
||||
)
|
||||
prediction_scope = "全局聚合数据"
|
||||
product_name = "全局销售数据"
|
||||
else:
|
||||
# 产品模型（默认）：聚合该产品在所有店铺的数据
|
||||
# 此时，传入的product_id是真正的产品ID
|
||||
product_df = aggregate_multi_store_data(
|
||||
product_id=product_id,
|
||||
aggregation_method='sum',
|
||||
|
||||
@ -21,7 +21,7 @@ from utils.visualization import plot_loss_curve
|
||||
from analysis.metrics import evaluate_model
|
||||
from core.config import DEVICE, DEFAULT_MODEL_DIR, LOOK_BACK, FORECAST_HORIZON
|
||||
|
||||
def train_product_model_with_kan(product_id, product_df=None, store_id=None, training_mode='product', aggregation_method='sum', epochs=50, sequence_length=LOOK_BACK, forecast_horizon=FORECAST_HORIZON, use_optimized=False, model_dir=DEFAULT_MODEL_DIR):
|
||||
def train_product_model_with_kan(product_id, model_identifier, product_df=None, store_id=None, training_mode='product', aggregation_method='sum', epochs=50, sequence_length=LOOK_BACK, forecast_horizon=FORECAST_HORIZON, use_optimized=False, model_dir=DEFAULT_MODEL_DIR):
|
||||
"""
|
||||
使用KAN模型训练产品销售预测模型
|
||||
|
||||
@ -282,7 +282,7 @@ def train_product_model_with_kan(product_id, product_df=None, store_id=None, tra
|
||||
'input_dim': input_dim,
|
||||
'output_dim': output_dim,
|
||||
'hidden_size': hidden_size,
|
||||
'hidden_sizes': [hidden_size, hidden_size*2, hidden_size],
|
||||
'hidden_sizes': [hidden_size, hidden_size * 2, hidden_size],
|
||||
'sequence_length': sequence_length,
|
||||
'forecast_horizon': forecast_horizon,
|
||||
'model_type': model_type_name,
|
||||
@ -299,7 +299,7 @@ def train_product_model_with_kan(product_id, product_df=None, store_id=None, tra
|
||||
|
||||
model_path = model_manager.save_model(
|
||||
model_data=model_data,
|
||||
product_id=product_id,
|
||||
product_id=model_identifier,
|
||||
model_type=model_type_name,
|
||||
version='v1', # KAN训练器默认使用v1
|
||||
store_id=store_id,
|
||||
|
||||
@ -25,8 +25,8 @@ from core.config import (
|
||||
)
|
||||
from utils.training_progress import progress_manager
|
||||
|
||||
def save_checkpoint(checkpoint_data: dict, epoch_or_label, product_id: str,
|
||||
model_type: str, model_dir: str, store_id=None,
|
||||
def save_checkpoint(checkpoint_data: dict, epoch_or_label, model_identifier: str,
|
||||
model_type: str, model_dir: str, store_id=None,
|
||||
training_mode: str = 'product', aggregation_method=None):
|
||||
"""
|
||||
保存训练检查点
|
||||
@ -47,7 +47,7 @@ def save_checkpoint(checkpoint_data: dict, epoch_or_label, product_id: str,
|
||||
os.makedirs(checkpoint_dir, exist_ok=True)
|
||||
|
||||
# 修正：直接使用product_id作为唯一标识符，因为它已经包含了store_前缀或药品ID
|
||||
filename = f"{model_type}_{product_id}_epoch_{epoch_or_label}.pth"
|
||||
filename = f"{model_type}_{model_identifier}_epoch_{epoch_or_label}.pth"
|
||||
|
||||
checkpoint_path = os.path.join(checkpoint_dir, filename)
|
||||
|
||||
@ -102,6 +102,7 @@ def load_checkpoint(product_id: str, model_type: str, epoch_or_label,
|
||||
|
||||
def train_product_model_with_mlstm(
|
||||
product_id,
|
||||
model_identifier,
|
||||
product_df,
|
||||
store_id=None,
|
||||
training_mode='product',
|
||||
@ -430,10 +431,11 @@ def train_product_model_with_mlstm(
|
||||
'output_dim': output_dim,
|
||||
'hidden_size': hidden_size,
|
||||
'num_heads': num_heads,
|
||||
'dropout': dropout_rate,
|
||||
'dropout_rate': dropout_rate,
|
||||
'num_blocks': num_blocks,
|
||||
'embed_dim': embed_dim,
|
||||
'dense_dim': dense_dim,
|
||||
'mlstm_layers': 2, # 确保这个参数被保存
|
||||
'sequence_length': sequence_length,
|
||||
'forecast_horizon': forecast_horizon,
|
||||
'model_type': 'mlstm'
|
||||
@ -450,13 +452,13 @@ def train_product_model_with_mlstm(
|
||||
}
|
||||
|
||||
# 保存检查点
|
||||
save_checkpoint(checkpoint_data, epoch + 1, product_id, 'mlstm',
|
||||
save_checkpoint(checkpoint_data, epoch + 1, model_identifier, 'mlstm',
|
||||
model_dir, store_id, training_mode, aggregation_method)
|
||||
|
||||
# 如果是最佳模型，额外保存一份
|
||||
if test_loss < best_loss:
|
||||
best_loss = test_loss
|
||||
save_checkpoint(checkpoint_data, 'best', product_id, 'mlstm',
|
||||
save_checkpoint(checkpoint_data, 'best', model_identifier, 'mlstm',
|
||||
model_dir, store_id, training_mode, aggregation_method)
|
||||
emit_progress(f"💾 保存最佳模型检查点 (epoch {epoch+1}, test_loss: {test_loss:.4f})")
|
||||
epochs_no_improve = 0
|
||||
@ -551,10 +553,11 @@ def train_product_model_with_mlstm(
|
||||
'output_dim': output_dim,
|
||||
'hidden_size': hidden_size,
|
||||
'num_heads': num_heads,
|
||||
'dropout': dropout_rate,
|
||||
'dropout_rate': dropout_rate,
|
||||
'num_blocks': num_blocks,
|
||||
'embed_dim': embed_dim,
|
||||
'dense_dim': dense_dim,
|
||||
'mlstm_layers': 2, # 确保这个参数被保存
|
||||
'sequence_length': sequence_length,
|
||||
'forecast_horizon': forecast_horizon,
|
||||
'model_type': 'mlstm'
|
||||
@ -575,7 +578,7 @@ def train_product_model_with_mlstm(
|
||||
|
||||
# 保存最终模型（使用epoch标识）
|
||||
final_model_path = save_checkpoint(
|
||||
final_model_data, f"final_epoch_{epochs}", product_id, 'mlstm',
|
||||
final_model_data, f"final_epoch_{epochs}", model_identifier, 'mlstm',
|
||||
model_dir, store_id, training_mode, aggregation_method
|
||||
)
|
||||
|
||||
|
||||
@ -21,8 +21,8 @@ from analysis.metrics import evaluate_model
|
||||
from core.config import DEVICE, DEFAULT_MODEL_DIR, LOOK_BACK, FORECAST_HORIZON
|
||||
from utils.training_progress import progress_manager
|
||||
|
||||
def save_checkpoint(checkpoint_data: dict, epoch_or_label, product_id: str,
|
||||
model_type: str, model_dir: str, store_id=None,
|
||||
def save_checkpoint(checkpoint_data: dict, epoch_or_label, model_identifier: str,
|
||||
model_type: str, model_dir: str, store_id=None,
|
||||
training_mode: str = 'product', aggregation_method=None):
|
||||
"""
|
||||
保存训练检查点
|
||||
@ -44,7 +44,7 @@ def save_checkpoint(checkpoint_data: dict, epoch_or_label, product_id: str,
|
||||
|
||||
# 生成检查点文件名
|
||||
# 修正：直接使用product_id作为唯一标识符，因为它已经包含了store_前缀或药品ID
|
||||
filename = f"{model_type}_{product_id}_epoch_{epoch_or_label}.pth"
|
||||
filename = f"{model_type}_{model_identifier}_epoch_{epoch_or_label}.pth"
|
||||
|
||||
checkpoint_path = os.path.join(checkpoint_dir, filename)
|
||||
|
||||
@ -56,6 +56,7 @@ def save_checkpoint(checkpoint_data: dict, epoch_or_label, product_id: str,
|
||||
|
||||
def train_product_model_with_tcn(
|
||||
product_id,
|
||||
model_identifier,
|
||||
product_df=None,
|
||||
store_id=None,
|
||||
training_mode='product',
|
||||
@ -381,6 +382,7 @@ def train_product_model_with_tcn(
|
||||
'output_dim': output_dim,
|
||||
'hidden_size': hidden_size,
|
||||
'num_layers': num_layers,
|
||||
'num_channels': [hidden_size] * num_layers,
|
||||
'dropout': dropout_rate,
|
||||
'kernel_size': kernel_size,
|
||||
'sequence_length': sequence_length,
|
||||
@ -398,13 +400,13 @@ def train_product_model_with_tcn(
|
||||
}
|
||||
|
||||
# 保存检查点
|
||||
save_checkpoint(checkpoint_data, epoch + 1, product_id, 'tcn',
|
||||
save_checkpoint(checkpoint_data, epoch + 1, model_identifier, 'tcn',
|
||||
model_dir, store_id, training_mode, aggregation_method)
|
||||
|
||||
# 如果是最佳模型，额外保存一份
|
||||
if test_loss < best_loss:
|
||||
best_loss = test_loss
|
||||
save_checkpoint(checkpoint_data, 'best', product_id, 'tcn',
|
||||
save_checkpoint(checkpoint_data, 'best', model_identifier, 'tcn',
|
||||
model_dir, store_id, training_mode, aggregation_method)
|
||||
emit_progress(f"💾 保存最佳模型检查点 (epoch {epoch+1}, test_loss: {test_loss:.4f})")
|
||||
|
||||
@ -471,6 +473,7 @@ def train_product_model_with_tcn(
|
||||
'output_dim': output_dim,
|
||||
'hidden_size': hidden_size,
|
||||
'num_layers': num_layers,
|
||||
'num_channels': [hidden_size] * num_layers,
|
||||
'dropout': dropout_rate,
|
||||
'kernel_size': kernel_size,
|
||||
'sequence_length': sequence_length,
|
||||
@ -494,7 +497,7 @@ def train_product_model_with_tcn(
|
||||
|
||||
# 保存最终模型（使用epoch标识）
|
||||
final_model_path = save_checkpoint(
|
||||
final_model_data, f"final_epoch_{epochs}", product_id, 'tcn',
|
||||
final_model_data, f"final_epoch_{epochs}", model_identifier, 'tcn',
|
||||
model_dir, store_id, training_mode, aggregation_method
|
||||
)
|
||||
|
||||
|
||||
@ -27,8 +27,8 @@ from core.config import (
|
||||
from utils.training_progress import progress_manager
|
||||
from utils.model_manager import model_manager
|
||||
|
||||
def save_checkpoint(checkpoint_data: dict, epoch_or_label, product_id: str,
|
||||
model_type: str, model_dir: str, store_id=None,
|
||||
def save_checkpoint(checkpoint_data: dict, epoch_or_label, model_identifier: str,
|
||||
model_type: str, model_dir: str, store_id=None,
|
||||
training_mode: str = 'product', aggregation_method=None):
|
||||
"""
|
||||
保存训练检查点
|
||||
@ -48,7 +48,7 @@ def save_checkpoint(checkpoint_data: dict, epoch_or_label, product_id: str,
|
||||
os.makedirs(checkpoint_dir, exist_ok=True)
|
||||
|
||||
# 修正：直接使用product_id作为唯一标识符，因为它已经包含了store_前缀或药品ID
|
||||
filename = f"{model_type}_{product_id}_epoch_{epoch_or_label}.pth"
|
||||
filename = f"{model_type}_{model_identifier}_epoch_{epoch_or_label}.pth"
|
||||
|
||||
checkpoint_path = os.path.join(checkpoint_dir, filename)
|
||||
|
||||
@ -60,6 +60,7 @@ def save_checkpoint(checkpoint_data: dict, epoch_or_label, product_id: str,
|
||||
|
||||
def train_product_model_with_transformer(
|
||||
product_id,
|
||||
model_identifier,
|
||||
product_df=None,
|
||||
store_id=None,
|
||||
training_mode='product',
|
||||
@ -399,13 +400,13 @@ def train_product_model_with_transformer(
|
||||
}
|
||||
|
||||
# 保存检查点
|
||||
save_checkpoint(checkpoint_data, epoch + 1, product_id, 'transformer',
|
||||
save_checkpoint(checkpoint_data, epoch + 1, model_identifier, 'transformer',
|
||||
model_dir, store_id, training_mode, aggregation_method)
|
||||
|
||||
# 如果是最佳模型，额外保存一份
|
||||
if test_loss < best_loss:
|
||||
best_loss = test_loss
|
||||
save_checkpoint(checkpoint_data, 'best', product_id, 'transformer',
|
||||
save_checkpoint(checkpoint_data, 'best', model_identifier, 'transformer',
|
||||
model_dir, store_id, training_mode, aggregation_method)
|
||||
emit_progress(f"💾 保存最佳模型检查点 (epoch {epoch+1}, test_loss: {test_loss:.4f})")
|
||||
epochs_no_improve = 0
|
||||
@ -501,7 +502,7 @@ def train_product_model_with_transformer(
|
||||
|
||||
# 保存最终模型（使用epoch标识）
|
||||
final_model_path = save_checkpoint(
|
||||
final_model_data, f"final_epoch_{epochs}", product_id, 'transformer',
|
||||
final_model_data, f"final_epoch_{epochs}", model_identifier, 'transformer',
|
||||
model_dir, store_id, training_mode, aggregation_method
|
||||
)
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user